© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 3677
    Prev
    Next
    INDEX
    Explanations

    words related to contrasts or opposing concepts

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    441
    +0.07
    0.5%
    235
    +0.06
    0.4%
    158
    +0.06
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    549
    +0.07
    0.07
    291
    +0.06
    0.09
    588
    +0.06
    0.09
    Negative Logits
     Annotations
    -0.57
    beans
    -0.51
     Cosponsors
    -0.50
    phones
    -0.49
     Qian
    -0.46
    çīĪ
    -0.46
    come
    -0.45
    bucks
    -0.45
     liner
    -0.45
    banks
    -0.45
    POSITIVE LOGITS
    etrical
    0.93
    etr
    0.83
    etric
    0.80
     pend
    0.68
     diam
    0.64
     oppos
    0.60
     antit
    0.57
     bombard
    0.57
    ãĤ¶
    0.57
     mathemat
    0.56
    Activations Density 9.378%

    No Known Activations